Claude Skills by paulasilvatech

Fully migrate a Backstage plugin to the new frontend system, dropping all old system support. Use this skill for internal plugins that only need to run in a single app, or when you are ready to remove backward compatibility entirely.

Add new frontend-system support to an existing Backstage plugin while retaining its legacy entry point. Use when published or shared plugins need dual compatibility, alpha exports, PageBlueprint extensions, route reuse, and both old and new app consumers.

Add new frontend system support to an existing Backstage plugin while keeping the old system working. Use this skill for published or shared plugins that need to work in both old and new frontend system apps.

Validates Open Horizons architecture Markdown documents for required sections, required diagrams, Mermaid structure, explanation completeness, and repository copy conventions. Use this skill when reviewing or finishing an architecture document, checking {app}_Architecture.md, verifying Mermaid diagrams, or confirming the architecture Definition of Done.

Select, explain, and apply cloud design patterns for distributed systems across reliability, performance, messaging, architecture, deployment, security, and event-driven categories. Use when designing, reviewing, or implementing cloud workloads and distributed system architectures.

Create a new repository-root llms.txt file from repository structure and documentation according to the llms.txt specification. Use when users ask to create llms.txt, generate LLM navigation, document repository structure for LLMs, or add an llms.txt compliant with https://llmstxt.org/.

Foundry agent blueprint maps agent designs to Azure AI Foundry Agent Service models, connections, tools, memory, evaluation, and tracing. Use this skill when designing Foundry agent runtimes, model catalog choices, Azure AI Search or Redis connections, Bing connections, OpenAPI tools, MCP tools, code interpreter, file search, threads, runs, or evaluation plans.

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle tiers (alpha, beta, rc, released) with CHANGELOG-driven selective bumps, floor bound checks, and post-bump validation.

Create, register, deploy, update, and synchronize prompt-based Azure AI Foundry agents from a local JSON manifest using the Agent Service REST API. Use when users ask to sync Foundry agents, create agents in Foundry, push agents, update agent instructions, scaffold a foundry-agents.json manifest, or add sync scripts.

Design evaluator-optimizer, reflection, rubric, LLM-as-judge, and test-driven refinement loops for AI agent outputs. Use when implementing self-critique, iterative improvement, quality gates, agent response evaluation, code refinement, or rubric-based scoring for generated code, reports, or analysis.

Azure AI Foundry operations provisions workspaces, model deployments, RAG resources, operational settings, and resource checks. Use this skill when provisioning AI Foundry, deploying OpenAI models, configuring RAG, operating model endpoints, setting up AI workspaces, or checking Foundry resources.

Designs, implements, reviews, and migrates Claude API integrations using official Anthropic SDKs or Claude models in Microsoft Foundry. Use when work involves Claude, Anthropic, Opus, Sonnet, Haiku, Messages API, tool use, streaming, caching, model migration, or Foundry-hosted Claude clients.

Guide ongoing development of CopilotKit frontends connected over AG-UI to Microsoft Agent Framework agents and Azure AI Foundry hosted agents. Use when adding or gating tools, wiring human-in-the-loop approval, building generative UI, synchronizing shared state, debugging AG-UI event streams, upgrading preview packages, or deploying hosted agent updates.

GitHub CLI operations use gh commands and GitHub API workflows for repositories, issues, pull requests, Actions, packages, repository discovery, GitHub App setup, and pull request automation. Use this skill when working with gh repo, gh pr, gh issue, gh workflow, gh run, gh api, Actions checks, or package operations.

Configures GitHub Codespaces devcontainer environments for Backstage Golden Path templates. Use this skill when creating or validating devcontainer.json, Codespaces setup, Python FastAPI templates, Node app templates, Terraform templates, Java templates, AI/ML pipelines, data pipelines, container features, SDK pre-installation, or template mapping.

Generates path-scoped GitHub Copilot migration instructions from actual branch, commit, tag, or release diffs. Use when handling framework upgrades, architecture refactors, technology migrations, dependency updates, API changes, and obsolete-pattern prevention.

Adopt or review repository-level harness engineering for GitHub Copilot and coding agents. Use when users want durable agent instructions, guardrails, regression checks, drift checks, failure memory, or adoption reports that prevent repeated AI coding-agent mistakes in a target repository.

Generate technology-agnostic blueprints for comprehensive copilot-instructions.md files that make GitHub Copilot follow exact project versions, architecture, code quality, documentation, testing, and versioning conventions discovered from the codebase. Use this skill when the user asks for configuration variables, wants to create copilot-instructions.md, or needs repository-specific GitHub Copilot coding guidance.

Builds applications with the GitHub Copilot SDK using explicit client lifecycle, sessions, permissions, streaming, tools, and MCP integration. Use when embedding Copilot in an application, creating sessions, handling events, registering tools, or troubleshooting SDK behavior.

Retrieve and display GitHub Copilot usage metrics for organizations and enterprises using the GitHub CLI, REST API, and bundled scripts. Use when the user asks about Copilot usage, adoption, active users, acceptance rates, suggestions, chat interactions, per-user breakdowns, organization metrics, enterprise metrics, or usage on a specific date.

Dispatches authorized GitHub issue-comment commands to read-only repository validation. Use when implementing or validating /check-agents, /help, issue comment authorization, command parsing, or IssueOps workflow behavior.

Pipeline diagnostics analyzes GitHub Actions CI/CD failures and remediation patterns. Use this skill when diagnosing workflow failures, build errors, deploy failures, failed jobs or steps, logs triage, actions permissions, OIDC failures, dependency cache issues, and CI/CD debugging.

Designs, implements, reviews, and evaluates Model Context Protocol servers in TypeScript or Python. Use when creating MCP tools, resources, prompts, transports, authentication, schemas, pagination, or server evaluations for an external API or service.

Use the MCP CLI to discover Model Context Protocol servers, inspect tool schemas, grep tool names, and call MCP tools with JSON, raw text, or stdin arguments. Use when the user asks to list MCP servers, inspect a server/tool schema, call an MCP tool from the command line, or script MCP access with --json or --raw output.

Create, update, refactor, explain, or review Microsoft Agent Framework applications, agents, workflows, and migrations in .NET or Python. Use this skill when working with Microsoft Agent Framework, successor guidance for Semantic Kernel or AutoGen, Azure AI Foundry, Azure OpenAI, OpenAI providers, MCP tools, workflows, middleware, checkpointing, or language-specific samples.

Look up official Microsoft API references, SDK signatures, packages, and working code samples before writing or fixing Azure SDK, .NET, Microsoft Graph, or Microsoft API code. Use when verifying method names, overloads, parameters, authentication patterns, package names, deprecations, RBAC errors, or suspected hallucinated Microsoft SDK calls.

Query official Microsoft documentation and adjacent source documentation for Azure, .NET, Agent Framework, Semantic Kernel, Aspire, VS Code, GitHub, Power Platform, Windows, and M365. Use this skill when the user needs concepts, tutorials, configuration details, API examples, code samples, or current docs for Microsoft ecosystem technologies.

Create hybrid GitHub Copilot skills for Microsoft technologies using Microsoft Learn MCP tools or the mslearn CLI. Use this skill when the user asks to create a skill for Azure, .NET, Microsoft 365, VS Code, Bicep, Semantic Kernel, a Microsoft SDK, an Azure service, a framework, or a Microsoft REST API.

Assesses read-only Azure readiness for one Open Horizons deployment scope using current subscription, provider, quota, SKU, identity, network, and resource evidence. Use when needed before Terraform planning or deployment when Azure prerequisites may block the requested components.

Operates and integrates the Open Horizons Agentic Engineering Graph (AEG) through Backstage with authenticated run management, G1/G2 decisions, traceability analytics, and golden-path harvesting. Use this skill when starting or inspecting AEG runs, reviewing gates, analyzing AEG evidence, proposing reusable profiles, or wiring the AEG feature into the Open Horizons portal.

Install and use Backstage's AI catalog model for AiResource skills and rules plus mcp-server API entities, ownership, lifecycle, relationships, and source locations. Use when cataloging AI skills, governance rules, agents, or MCP servers.

Create or assess a standalone Backstage adopter application with version-aware prerequisites, package layout, first-run configuration, and baseline validation. Use when starting a Backstage app, reinstalling an app shell, or checking whether a repository is a valid adopter app.

Design, edit, validate, and troubleshoot Backstage app configuration, environment overlays, schemas, secrets, integrations, and frontend visibility. Use when working with app-config YAML, BACKSTAGE_ENV, config:check, deployment overrides, or configuration errors.

Configure, review, and troubleshoot Backstage sign-in, identity resolvers, auth providers, delegated third-party access, callbacks, and permissions. Use when setting up GitHub, Microsoft, guest, proxy, or custom auth providers or fixing login failures.

Run and compare the Backstage catalog query performance battery against a safe database replica, capture PostgreSQL plans and buffers, detect regressions, and update the baseline. Use when changing catalog queries, indexes, schemas, or database performance behavior.

Model, register, discover, validate, and troubleshoot Backstage Software Catalog entities, providers, processors, ownership, relations, locations, and lifecycle. Use when handling catalog-info YAML, entity ingestion, org discovery, duplicate entities, or catalog governance.

Prepare, implement, validate, and document contributions to backstage/backstage or a close fork using targeted tests, exact root typechecking, formatting, linting, API reports, changesets, DCO, and Apache headers. Use when changing Backstage core packages, plugins, docs, or contributor workflows.

Configure, secure, and validate Backstage technical integrations with GitHub, Azure and Azure DevOps, and ServiceNow across catalog discovery, events, software templates, CI/CD views, incidents, and provider credentials. Use when setting up or troubleshooting integrations outside user sign-in.

Choose and implement Backstage framework extension points, core backend services, frontend blueprints, service refs, modules, lifecycle, auth, permissions, schedulers, tracing, metrics, and generated API references. Use when designing plugin architecture or selecting supported framework APIs.

Install, configure, authorize, and troubleshoot Backstage Kubernetes frontend and backend plugins, cluster discovery, entity annotations, authentication, permissions, proxies, custom resources, and service-owner views. Use when working with Kubernetes tabs, clusters, pods, or integration errors.

Register typed Backstage backend actions and expose selected actions as authenticated MCP tools with schemas, attributes, permissions, filters, server instructions, and well-known action validation. Use when configuring the Actions Registry, Actions Service, MCP Actions Backend, or AI tool exposure.

Install, configure, emit, process, route, and troubleshoot Backstage notifications and optional real-time signals. Use when handling user or group notifications, external emitters, email or Slack processors, scaffolder notifications, settings, topics, or delivery failures.

Operate, monitor, troubleshoot, and harden production Backstage services, databases, schedulers, integrations, health endpoints, logs, and deployments. Use when handling startup failures, readiness problems, database errors, provider refresh issues, performance incidents, or production runbooks.

Design, implement, test, and troubleshoot Backstage permission policies, basic and resource permissions, conditional decisions, rules, frontend authorization, and plugin integration. Use when implementing RBAC, ABAC, resource filtering, action visibility, or fixing authorization failures.

Install, configure, extend, operate, and troubleshoot Backstage Search frontends, engines, collators, indices, result extensions, filters, schedules, and permissions. Use when working with search pages, Catalog or TechDocs indexing, custom collators, Postgres or Elasticsearch, or missing results.

Design, implement, validate, and troubleshoot Backstage Software Templates, custom actions, Golden Paths, skeleton rendering, repository publication, and catalog registration. Use when working with template.yaml, scaffolder actions, parameters, step outputs, or template execution failures.

Configure, build, preview, publish, migrate, and troubleshoot Backstage TechDocs and MkDocs content. Use when handling techdocs-ref annotations, mkdocs.yml, local or external builders, object-storage publishers, CI generation, broken docs, or wiki-to-TechDocs migration.

Plan, execute, and validate Backstage application or plugin dependency upgrades with release-aware package alignment, migrations, config review, changesets, and rollback. Use when bumping Backstage versions, resolving package skew, adopting new systems, or preparing an upgrade PR.

Implements focused changes in an existing repository through evidence-driven diagnosis, minimal edits, immediate checks, and proportionate regression validation. Use when handling bug fixes, features, improvements, refactoring, modernization, tests, and documentation updates.

Coordinates end-to-end Open Horizons platform deployment across prerequisites, Terraform, Kubernetes, GitOps, and verification. Use this skill when planning or executing full platform deployment, dry-run deployment, horizon enablement, deployment sequence, post-deploy verification, or deployment troubleshooting.